Stories from the gateway
Cost & Pricing
AI Cost Anomaly Detection That Catches Real Problems
How to spot abnormal LLM spend in token data: per-workload baselines, rate-of-change thresholds, and telling a runaway agent apart from real growth.
· 11 min readCost & Pricing
Alerting on Token Spikes Before the Invoice Explains Them
Runaway LLM spend is usually discovered at month end. What to alert on, what thresholds actually work, and how to avoid alarms nobody reads.
· 8 min read
AI Agents
Approval Gates in Agents: Where to Put the Human
· 9 min read
Models
Arena Elo Explained: What a Preference Rating Measures
· 9 min read
Fundamentals
Attention Mechanisms Explained Without the Linear Algebra
· 9 min readCost & Pricing
Batch API Savings: Trading Latency for a Real Discount
· 8 min read
Fundamentals
Batch Size and Throughput: The Trade Behind Every Token Price
· 9 min read
Fundamentals
Beam Search vs Sampling: Why Chat Models Do Not Search
· 9 min read
Models
Benchmark Contamination Explained, and What to Do About It
· 9 min read
Models
Best Model for Agentic Workflows: Reliability Compounds
· 9 min readModels
Best Model for Backend Code: Where Benchmarks Transfer Best
· 9 min read
Models
Best Model for Batch Jobs: Throughput, Not Intelligence
· 8 min read
Models
Best Model for Data Science: Correct Code, Wrong Analysis
· 9 min read
Models
Best Model for DevOps: Blast Radius Changes the Calculus
· 9 min readReady to start?
Every model, one key. Start free and upgrade when you are ready.